A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
[ROCM] Bind triton version to 3.2 in requirements-built.txt (#16664)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Sage Moore committed
Apr 15, 2025 at 23:05 UTC
44fa4d556c37cf3538090960bb3e07654193df5e
1 file changed
+1
requirements/rocm-build.txt
+1
@@ -6,6 +6,7 @@ torch==2.6.0
6
torchvision==0.21.0
7
torchaudio==2.6.0
8
9
+triton==3.2
10
cmake>=3.26,<4
11
packaging
12
setuptools>=61